Why agents make autonomous decisions in Prompt Engineering / GenAI - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define an agent that makes decisions without human input.

Prompt Engineering / GenAI

class Agent:
    def __init__(self):
        self.state = None

    def decide(self, environment):
        return [1]

Drag options to blanks, or click blank then click option'

Aprint('Hello World')

Benvironment.get_best_action()

Cself.state = None

Dreturn None

Attempts:

3 left

💡 Hint

Common Mistakes

Returning None instead of an action.

Using print statements instead of returning an action.

The agent decides by choosing the best action from the environment, enabling autonomous decisions.

2fill in blank

medium

Complete the code to update the agent's state after taking an action.

Prompt Engineering / GenAI

class Agent:
    def __init__(self):
        self.state = None

    def update_state(self, action):
        self.state = [1]

Drag options to blanks, or click blank then click option'

Aself.state

BNone

Cprint(action)

Daction

Attempts:

3 left

💡 Hint

Common Mistakes

Setting state to None instead of the action.

Using print instead of assignment.

The agent updates its internal state to the action it just took, reflecting autonomous decision-making.

3fill in blank

hard

Fix the error in the agent's decision method to return an action string.

Prompt Engineering / GenAI

class Agent:
    def decide(self):
        action = 'move_forward'
        [1] action

Drag options to blanks, or click blank then click option'

Areturn

Bpass

Cyield

Dprint

Attempts:

3 left

💡 Hint

Common Mistakes

Using print instead of return.

Using pass which does nothing.

The decide method must return the action string so the agent can act autonomously.

4fill in blank

hard

Fill both blanks to create a dictionary of actions and their rewards for autonomous decision making.

Prompt Engineering / GenAI

rewards = { 'move': [1], 'stop': [2] }

Drag options to blanks, or click blank then click option'

A10

B0

C-5

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Assigning negative reward to 'move' which discourages action.

Using None instead of numeric rewards.

The 'move' action has a positive reward (10), encouraging the agent to move, while 'stop' has zero reward.

5fill in blank

hard

Fill all three blanks to create a function that selects the best action based on rewards.

Prompt Engineering / GenAI

def best_action(actions, rewards):
    best = None
    max_reward = [1]
    for action in actions:
        if rewards[action] [2] max_reward:
            best = action
            max_reward = rewards[action]
    return [3]

Drag options to blanks, or click blank then click option'

Afloat('inf')

B>

Cbest

Dfloat('-inf')

Attempts:

3 left

💡 Hint

Common Mistakes

Initializing max_reward to positive infinity.

Using '<' instead of '>' in comparison.

Returning None instead of best action.

Initialize max_reward to negative infinity to find max; use '>' to compare; return best action.